Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: ICE and two conditions

From   Richard Williams <>
Subject   Re: st: ICE and two conditions
Date   Thu, 01 Dec 2011 14:55:20 -0500

At 02:22 PM 12/1/2011, daniel klein wrote:
I feel I have to clarify something here. My statement was mainly
concerned with a quick solution to the problem at hand and might well
have sounded a bit too general. I appologize.

I did not want to state, that you should prefer -mi impute chained-
over -ice- or that -ice- is completely useless now that Stata 12 is

From it is clear,
that at least -ice- includes "stepwise model selection" which -mi
impute chained- does not. I have not looked into the code, but Yulia
Marchenko states that -mi chained- and -ice- use the same method,
which makes me believe there should not be a reason to prefer one or
the other. I would like to hear others to comment on this issue,
especially on passive imputation (e.g. interactions). I could imagine
a gain in execution time of -mi impute chained- over -ice- when using
Stata MP.

Thanks for the clarifications. Previous posts on Statalist have argued against using passive imputation. See

Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index